jacob-recastai commited on
Commit
58e02d6
1 Parent(s): 029aa26

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +23 -17
  2. tokenizer.json +2 -2
  3. tokenizer_config.json +4 -4
special_tokens_map.json CHANGED
@@ -1,23 +1,29 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "<|im_start|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<|im_end|>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
  ],
18
- "bos_token": "<bos>",
19
- "eos_token": "<eos>",
20
- "pad_token": "<pad>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "unk_token": {
22
  "content": "<unk>",
23
  "lstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
  "unk_token": {
28
  "content": "<unk>",
29
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:376f7d962ebaed8fbd7b003204ab85d5eaaf08c3515aa607b0252255fa9160a1
3
- size 17477929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
3
+ size 17477473
tokenizer_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "add_bos_token": true,
3
  "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
@@ -34,7 +34,7 @@
34
  "single_word": false,
35
  "special": true
36
  },
37
- "256000": {
38
  "content": "<|im_start|>",
39
  "lstrip": false,
40
  "normalized": false,
@@ -42,7 +42,7 @@
42
  "single_word": false,
43
  "special": true
44
  },
45
- "256001": {
46
  "content": "<|im_end|>",
47
  "lstrip": false,
48
  "normalized": false,
@@ -56,7 +56,7 @@
56
  "<|im_end|>"
57
  ],
58
  "bos_token": "<bos>",
59
- "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{'<bos>'}}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ '<eos>' }}{% endif %}",
60
  "clean_up_tokenization_spaces": false,
61
  "eos_token": "<eos>",
62
  "legacy": null,
 
1
  {
2
+ "add_bos_token": false,
3
  "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
 
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "106": {
38
  "content": "<|im_start|>",
39
  "lstrip": false,
40
  "normalized": false,
 
42
  "single_word": false,
43
  "special": true
44
  },
45
+ "107": {
46
  "content": "<|im_end|>",
47
  "lstrip": false,
48
  "normalized": false,
 
56
  "<|im_end|>"
57
  ],
58
  "bos_token": "<bos>",
59
+ "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
60
  "clean_up_tokenization_spaces": false,
61
  "eos_token": "<eos>",
62
  "legacy": null,